Please disclose if any significant portion of your mod was created using AI tools by adding the 'AI Generated' category. Failing to do so may result in the mod being removed from Thunderstore.
EchoMimics
Context-aware Masked enemies that locally clone crewmate voices with Audio8 and answer with Qwen3.5.
CHANGELOG
Changelog
0.1.1
- Reworked the README into a complete first-time user guide.
- Improved Windows Python and Ollama detection.
- Added model preloading so setup downloads and verifies Whisper and Audio8 before the first game.
- Added continuous GitHub build, test, package validation, and artifact checks.
0.1.0
- Added local ambient speech detection and bounded multiplayer voice relay.
- Added local faster-whisper transcription.
- Added contextual round memory and Qwen3.5 2B dialogue generation through Ollama.
- Added Audio8 TTS 0.1B voice cloning for each Masked enemy's copied crewmate.
- Added spatial generated voice playback for all modded players.
- Added explicit per-player voice-capture consent that defaults to disabled.
- Added automatic round-data cleanup, request limits, and loopback-only runtime defaults.
- Added Windows setup and launch scripts.
- Added runtime tests, build checks, package checks, and Thunderstore packaging.
